Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2665 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.7049. Min Act: -0.0001

Data Index: 868047 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6963. Min Act: -0.0001

Data Index: 642555 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6204. Min Act: -0.0001

Data Index: 992590 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6754. Min Act: -0.0001

Data Index: 787861 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6645. Min Act: -0.0001

Data Index: 1981 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6210. Min Act: -0.0001

Data Index: 1009904 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6429. Min Act: -0.0001

Data Index: 528443 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6510. Min Act: -0.0001

Data Index: 785783 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6292. Min Act: -0.0001

Data Index: 1272475 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5973. Min Act: -0.0001

Data Index: 506850 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5672. Min Act: -0.0001

Data Index: 647479 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6049. Min Act: -0.0001

Data Index: 511624 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5645. Min Act: -0.0001

Data Index: 615983 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5846. Min Act: -0.0001

Data Index: 1234454 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6015. Min Act: -0.0001

Data Index: 997197 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5563. Min Act: -0.0001

Data Index: 382475 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6048. Min Act: -0.0001

Data Index: 1153218 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.6017. Min Act: -0.0001

Data Index: 664766 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5425. Min Act: -0.0001

Data Index: 502676 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5797. Min Act: -0.0001

Data Index: 1090399 (C4 (Web Text))

Max Activating Token Index: 194